Energy-Based Reasoners: Your Recurrent Reasoner Should Be an Energy-Based Model
Abstract
Energy-Based Reasoners guide looped latent reasoning by learning an energy function whose gradient refines states and signals when to stop, with exploration-based training improving performance and efficiency.
Looping is a powerful inductive bias for reasoning. By repeatedly iterating a recurrent block, looped models can scale their effective depth and enable multi-step reasoning in latent space. However, existing looped models are not inherently guided by an explicit measure of progress, making it difficult to determine when to stop looping and how to improve upon the current state. To enable this, we introduce Energy-Based Reasoners (EBRs), which learn an energy function over latent reasoning states and formulate looped updates as gradient descent on this energy. The energy scores latent states, while its gradient guides refinement and provides a signal for stopping. To train EBRs effectively, we further introduce exploration-based training to discover additional modes and to better shape the energy landscape over a broader set of states. Across four algorithmic reasoning benchmarks, EBRs match or outperform prior recurrent reasoning models, achieving 99.9% accuracy on Sudoku-Extreme while using 345times less inference compute than the next-best model and maintaining comparable training compute. On all multi-solution benchmarks, EBRs achieve state-of-the-art coverage of distinct valid solutions while maintaining near-100% single-sample accuracy. These results suggest that energy-based models are a promising approach for strong reasoning performance.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Classical Energies Learn to Reason 1,000x Faster than Looped Models (2026)
- Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals (2026)
- LoopCD: Loop-wise Contrastive Decoding for Improving Reasoning in Looped Language Models (2026)
- Invariant-Measure Reasoners: Stable Representations for Latent Reasoning (2026)
- From Chain-of-Thought to Loops: Non-Autoregressive Latent Reasoning via Looped Transformers (2026)
- Looped Reasoning Finishes Earlier Than You Think (2026)
- Dynamic K-Head: Difficulty-Supervised Budget Selection for Continuous Latent Reasoning (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2611.08977 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper